TY - GEN
T1 - Context-Gloss Augmentation for Improving Arabic Target Sense Verification
AU - Malaysha, Sanad
AU - Jarrar, Mustafa
AU - Khalilia, Mohammed
N1 - Publisher Copyright:
© 2023 12th Global Wordnet Conference, GWC 2023. All rights reserved.
PY - 2023/1/27
Y1 - 2023/1/27
N2 - Arabic language lacks semantic datasets and sense inventories. The most common semantically-labeled dataset for Arabic is the ArabGlossBERT, a relatively small dataset that consists of 167K context-gloss pairs (about 60K positive and 107K negative pairs), collected from Arabic dictionaries. This paper presents an enrichment to the ArabGlossBERT dataset, by augmenting it using (Arabic-English-Arabic) machine back-translation. Augmentation increased the dataset size to 352K pairs (149K positive and 203K negative pairs). We measure the impact of augmentation using different data configurations to fine-tune BERT on target sense verification (TSV) task. Overall, the accuracy ranges between 78% to 84% for different data configurations. Although our approach performed at par with the baseline, we did observe some improvements for some POS tags in some experiments. Furthermore, our fine-tuned models are trained on a larger dataset covering larger vocabulary and contexts. We provide an in-depth analysis of the accuracy for each part-of-speech (POS).
AB - Arabic language lacks semantic datasets and sense inventories. The most common semantically-labeled dataset for Arabic is the ArabGlossBERT, a relatively small dataset that consists of 167K context-gloss pairs (about 60K positive and 107K negative pairs), collected from Arabic dictionaries. This paper presents an enrichment to the ArabGlossBERT dataset, by augmenting it using (Arabic-English-Arabic) machine back-translation. Augmentation increased the dataset size to 352K pairs (149K positive and 203K negative pairs). We measure the impact of augmentation using different data configurations to fine-tune BERT on target sense verification (TSV) task. Overall, the accuracy ranges between 78% to 84% for different data configurations. Although our approach performed at par with the baseline, we did observe some improvements for some POS tags in some experiments. Furthermore, our fine-tuned models are trained on a larger dataset covering larger vocabulary and contexts. We provide an in-depth analysis of the accuracy for each part-of-speech (POS).
UR - https://www.scopus.com/pages/publications/85184521725
M3 - Conference contribution
AN - SCOPUS:85184521725
T3 - 12th Global Wordnet Conference, GWC 2023
SP - 254
EP - 262
BT - 12th Global Wordnet Conference, GWC 2023
A2 - Rigau, German
A2 - Bond, Francis
A2 - Rademaker, Alexandre
PB - Association for Computational Linguistics (ACL)
T2 - 12th Global Wordnet Conference, GWC 2023
Y2 - 23 January 2023 through 27 January 2023
ER -